@inproceedings{boscher-etal-2025-enhancing,
title = "Enhancing Low-Resource Text Classification with {LLM}-Generated Corpora : A Case Study on Olfactory Reference Extraction",
author = {Boscher, C{\'e}dric and
Bruderer, Shannon and
Largeron, Christine and
Eglin, V{\'e}ronique and
Egyed-Zsigmond, El{\"o}d},
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.161/",
pages = "3004--3027",
ISBN = "979-8-89176-298-5",
abstract = "Extracting sensory information from text, particularly olfactory references, is challenging due to limited annotated datasets and the implicit, subjective nature of sensory experiences. This study investigates whether GPT-4o-generated data can complement or replace human annotations. We evaluate human- and LLM-labeled corpora on two tasks: coarse-grained detection of olfactory content and fine-grained sensory term extraction. Despite lexical variation, generated texts align well with real data in semantic and sensorimotor embedding spaces. Models trained on synthetic data perform strongly, especially in low-resource settings. Human annotations offer better recall by capturing implicit and diverse aspects of sensoriality, while GPT-4o annotations show higher precision through clearer pattern alignment. Data augmentation experiments confirm the utility of synthetic data, though trade-offs remain between label consistency and lexical diversity. These findings support using synthetic data to enhance sensory information mining when annotated data is limited."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boscher-etal-2025-enhancing">
<titleInfo>
<title>Enhancing Low-Resource Text Classification with LLM-Generated Corpora : A Case Study on Olfactory Reference Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cédric</namePart>
<namePart type="family">Boscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shannon</namePart>
<namePart type="family">Bruderer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Largeron</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Eglin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elöd</namePart>
<namePart type="family">Egyed-Zsigmond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Extracting sensory information from text, particularly olfactory references, is challenging due to limited annotated datasets and the implicit, subjective nature of sensory experiences. This study investigates whether GPT-4o-generated data can complement or replace human annotations. We evaluate human- and LLM-labeled corpora on two tasks: coarse-grained detection of olfactory content and fine-grained sensory term extraction. Despite lexical variation, generated texts align well with real data in semantic and sensorimotor embedding spaces. Models trained on synthetic data perform strongly, especially in low-resource settings. Human annotations offer better recall by capturing implicit and diverse aspects of sensoriality, while GPT-4o annotations show higher precision through clearer pattern alignment. Data augmentation experiments confirm the utility of synthetic data, though trade-offs remain between label consistency and lexical diversity. These findings support using synthetic data to enhance sensory information mining when annotated data is limited.</abstract>
<identifier type="citekey">boscher-etal-2025-enhancing</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.161/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>3004</start>
<end>3027</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Low-Resource Text Classification with LLM-Generated Corpora : A Case Study on Olfactory Reference Extraction
%A Boscher, Cédric
%A Bruderer, Shannon
%A Largeron, Christine
%A Eglin, Véronique
%A Egyed-Zsigmond, Elöd
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F boscher-etal-2025-enhancing
%X Extracting sensory information from text, particularly olfactory references, is challenging due to limited annotated datasets and the implicit, subjective nature of sensory experiences. This study investigates whether GPT-4o-generated data can complement or replace human annotations. We evaluate human- and LLM-labeled corpora on two tasks: coarse-grained detection of olfactory content and fine-grained sensory term extraction. Despite lexical variation, generated texts align well with real data in semantic and sensorimotor embedding spaces. Models trained on synthetic data perform strongly, especially in low-resource settings. Human annotations offer better recall by capturing implicit and diverse aspects of sensoriality, while GPT-4o annotations show higher precision through clearer pattern alignment. Data augmentation experiments confirm the utility of synthetic data, though trade-offs remain between label consistency and lexical diversity. These findings support using synthetic data to enhance sensory information mining when annotated data is limited.
%U https://aclanthology.org/2025.ijcnlp-long.161/
%P 3004-3027
Markdown (Informal)
[Enhancing Low-Resource Text Classification with LLM-Generated Corpora : A Case Study on Olfactory Reference Extraction](https://aclanthology.org/2025.ijcnlp-long.161/) (Boscher et al., IJCNLP-AACL 2025)
ACL